book

The Applied TensorFlow and Keras Workshop

by Harveen Singh Chadha, Luis Capelo, Abhranshu Bagchi, Achint Chaudhary, Vishal Chauhan, Alexis Rutherford, Subhash Sundaravadivelu

July 2020

Intermediate to advanced

174 pages

3h 1m

English

Packt Publishing

Read now

Unlock full access

About the BookAudienceAbout the ChaptersConventionsCode PresentationSetting up Your EnvironmentInstallationInstalling Python on WindowsInstalling Python on LinuxInstalling Python on macOSInstalling pipJupyter NotebookJupyterLabInstalling LibrariesAccessing the Code Files
IntroductionWhat are Neural Networks?Successful Applications of Neural NetworksWhy Do Neural Networks Work So Well?Representation LearningFunction ApproximationLimitations of Deep LearningInherent Bias and Ethical ConsiderationsCommon Components and Operations of Neural NetworksConfiguring a Deep Learning EnvironmentSoftware Components for Deep LearningPython 3TensorFlowKerasTensorBoardJupyter Notebook, Pandas, and NumPyExercise 1.01: Verifying the Software ComponentsExploring a Trained Neural NetworkThe MNIST DatasetTraining a Neural Network with TensorFlowExercise 1.02: Training a Neural Network Using the MNIST DatasetTesting Network Performance with Unseen DataActivity 1.01: Training a Neural Network with Different HyperparametersSummary
IntroductionChoosing the Right Model ArchitectureConvolutional Neural Networks (CNNs)Recurrent Neural Networks (RNNs)Long Short-Term Memory (LSTM) NetworksGenerative Adversarial NetworksDeep Reinforcement Learning (DRL)Data NormalizationZ-ScorePoint-Relative NormalizationMaximum and Minimum NormalizationStructuring Your ProblemJupyter NotebookExercise 2.01: Exploring the Bitcoin Dataset and Preparing Data for a ModelUsing Keras as a TensorFlow InterfaceModel ComponentsExercise 2.02: Creating a TensorFlow Model Using KerasFrom Data Preparation to ModelingTraining a Neural NetworkReshaping Time Series DataMaking PredictionsOverfittingActivity 2.01: Assembling a Deep Learning SystemSummary
IntroductionProblem CategoriesLoss Functions, Accuracy, and Error RatesDifferent Loss Functions, Same ArchitectureUsing TensorBoardImplementing Model Evaluation MetricsEvaluating the Bitcoin ModelOverfittingModel PredictionsInterpreting PredictionsExercise 3.01: Creating an Active Training EnvironmentHyperparameter OptimizationLayers and Nodes – Adding More LayersAdding More NodesLayers and Nodes – ImplementationEpochsEpochs – ImplementationActivation FunctionsLinear (Identity) FunctionsHyperbolic Tangent (Tanh) FunctionRectified Linear Unit FunctionsActivation Functions – ImplementationRegularization StrategiesL2 RegularizationDropoutRegularization Strategies – ImplementationOptimization ResultsActivity 3.01: Optimizing a Deep Learning ModelSummary
IntroductionHandling New DataSeparating Data and ModelThe Data ComponentThe Model ComponentDealing with New DataRetraining an Old ModelTraining a New ModelExercise 4.01: Retraining a Model DynamicallyDeploying a Model as a Web ApplicationApplication Architecture and TechnologiesExercise 4.02: Deploying and Using CryptonicActivity 4.01: Deploying a Deep Learning ApplicationSummary
1. Introduction to Neural Networks and Deep LearningActivity 1.01: Training a Neural Network with Different Hyperparameters2. Real-World Deep Learning: Predicting the Price of BitcoinActivity 2.01: Assembling a Deep Learning System3. Real-World Deep Learning: Evaluating the Bitcoin ModelActivity 3.01: Optimizing a Deep Learning Model4. ProductizationActivity 4.01: Deploying a Deep Learning Application

Content preview from The Applied TensorFlow and Keras Workshop

4. Productization

Overview

In this chapter, you will handle new data and create a model that is able to learn continuously from the patterns it is shown and help make better predictions. We will use a web application as an example to show how to deploy deep learning models not only because of the simplicity and prevalence of web apps, but also the different possibilities they provide, such as getting predictions on mobile using a web browser and making REST APIs for users.

Introduction

This chapter focuses on how to productize a deep learning model. We use the word productize to define the creation of a software product from a deep learning model that can be used by other people and applications.

We are interested in models that use new ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Start your free trial

Publisher Resources

ISBN: 9781800201217Supplemental Content

The Applied TensorFlow and Keras Workshop

by Harveen Singh Chadha, Luis Capelo, Abhranshu Bagchi, Achint Chaudhary, Vishal Chauhan, Alexis Rutherford, Subhash Sundaravadivelu

4. Productization

Introduction

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

You might also like

The TensorFlow Workshop

The Deep Learning with Keras Workshop

TensorFlow 2 Pocket Reference

TensorFlow 2 Reinforcement Learning Cookbook

Publisher Resources

4. Productization

Introduction

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,and much more.

You might also like

The TensorFlow Workshop

The Deep Learning with Keras Workshop

TensorFlow 2 Pocket Reference

TensorFlow 2 Reinforcement Learning Cookbook

Publisher Resources

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.